PGx: all CPIC gene kinds — G6PD, variant-based, HLA tags, *0 CN genes (PGX-006/007/021)

- DB build resolves the PGX-007 tag variants from the manifest's probes; coverage over all gene kinds.
- Variant-based genes reported per variant (rs.. REF/ALT | Reference) with the CPIC lowest-activity diplotype;
  tagging genes as positive/negative with the population caveat; GSTM1/GSTT1/UGT2B17 *0 from targeted CN.
- Case-insensitive phenotype keys (MT-RNR1). GeT-RM check extended to VKORC1 and the CN genes:
  131/144 gene calls (docs/validation/V2_pgx_star.md).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv

src/simurg/pgx/phenotype.py

@@ -48,16 +48,24 @@ def build_table(gene: str, rows: list[tuple[str, str | None, str]], alleles: lis
     by_key: dict[str, tuple[str, str | None]] = {}
     totals: dict[float, str] = {}
     for key, total, pheno in rows:
-        k = json.dumps(json.loads(key), sort_keys=True)
+        k = _canon(json.loads(key))
         by_key.setdefault(k, (pheno, total))
         t = _num(total)
         if t is not None:
             totals.setdefault(t, pheno)
-    func = {a: f for a, f, _ in alleles}
+    func: dict[str, str | None] = {a: f.lower() for a, f, _ in alleles if f}
     act = {a: _num(v) for a, _, v in alleles}
     return GuidelineTable(gene, by_key, sorted(totals.items()), func, act)
 
 
+def _canon(counts: dict[str, int]) -> str:
+    """Case-insensitive lookup key (CPIC mixes "Normal risk …" and "normal risk …", MT-RNR1)."""
+    merged: dict[str, int] = {}
+    for k, v in counts.items():
+        merged[k.lower()] = merged.get(k.lower(), 0) + v
+    return json.dumps(merged, sort_keys=True)
+
+
 def _split(allele: str) -> tuple[str, int]:
     m = re.fullmatch(r"(.+?)x(\d+|N)", allele)
     if not m:
@@ -80,7 +88,7 @@ def phenotype(t: GuidelineTable, haplotypes: tuple[str, ...]) -> PhenotypeResult
         for v in vals:
             s = f"{v:.1f}" if abs(v * 10 - round(v * 10)) < 1e-9 else f"{v:g}"
             counts[s] = counts.get(s, 0) + 1
-        key = json.dumps(counts, sort_keys=True)
+        key = _canon(counts)
         total = sum(vals)
         hit = t.by_key.get(key)
         if hit is not None:
@@ -92,13 +100,13 @@ def phenotype(t: GuidelineTable, haplotypes: tuple[str, ...]) -> PhenotypeResult
     funcs: dict[str, int] = {}
     for h in haplotypes:
         core, n = _split(h)
-        f = "No function" if core in deletion else t.function.get(core)
+        f = "no function" if core in deletion else t.function.get(core)
         if f is None:
             return PhenotypeResult("Indeterminate", None, ["phenotype_not_in_guideline"])
         if n > 1:
             return PhenotypeResult("Indeterminate", None, ["phenotype_not_in_guideline"])  # no CPIC rule for xN here
         funcs[f] = funcs.get(f, 0) + 1
-    hit = t.by_key.get(json.dumps(funcs, sort_keys=True))
+    hit = t.by_key.get(_canon(funcs))
     if hit is None:
         return PhenotypeResult("Indeterminate", None, ["phenotype_not_in_guideline"])
     return PhenotypeResult(hit[0], None)

src/simurg/pgx/star.py

@@ -40,6 +40,9 @@ class GeneModel:
     freq: F64  # (H,) population frequency of each haplotype (prior)
     deletion_allele: str | None = None  # named whole-gene deletion (CYP2D6 *5), or "*0"
     reference: str = ""
+    basis: str = "star_allele"  # PGX-002 result basis: star_allele | haplotype_named | variant_based | tagging_variant
+    activity: dict[str, float] = field(default_factory=dict)  # allele → activity value (variant-based ordering)
+    function: dict[str, str] = field(default_factory=dict)
 
 
 @dataclass